Wang Zejin, Liu Jing, Chen Xi, Li Guoqing, Han Hua
National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, 95 Zhongguancun East Road, Beijing, 100190, China.
School of Artificial Intelligence, University of Chinese Academy of Sciences, 19 Yuquan Road, Beijing, 100190, China.
BioData Min. 2021 Feb 1;14(1):10. doi: 10.1186/s13040-021-00236-z.
Microscopic imaging is a crucial technology for visualizing neural and tissue structures. Large-area defects inevitably occur during the imaging process of electron microscope (EM) serial slices, which lead to reduced registration and semantic segmentation, and affect the accuracy of 3D reconstruction. The continuity of biological tissue among serial EM images makes it possible to recover missing tissues utilizing inter-slice interpolation. However, large deformation, noise, and blur among EM images remain the task challenging. Existing flow-based and kernel-based methods have to perform frame interpolation on images with little noise and low blur. They also cannot effectively deal with large deformations on EM images.
In this paper, we propose a sparse self-attention aggregation network to synthesize pixels following the continuity of biological tissue. First, we develop an attention-aware layer for consecutive EM images interpolation that implicitly adopts global perceptual deformation. Second, we present an adaptive style-balance loss taking the style differences of serial EM images such as blur and noise into consideration. Guided by the attention-aware module, adaptively synthesizing each pixel aggregated from the global domain further improves the performance of pixel synthesis. Quantitative and qualitative experiments show that the proposed method is superior to the state-of-the-art approaches.
The proposed method can be considered as an effective strategy to model the relationship between each pixel and other pixels from the global domain. This approach improves the algorithm's robustness to noise and large deformation, and can accurately predict the effective information of the missing region, which will greatly promote the data analysis of neurobiological research.
显微成像技术是观察神经和组织结构的关键技术。在电子显微镜（EM）连续切片成像过程中不可避免地会出现大面积缺损，这会导致配准和语义分割效果下降，并影响三维重建的准确性。连续EM图像中生物组织的连续性使得利用切片间插值来恢复缺失组织成为可能。然而，EM图像间的大变形、噪声和模糊仍然是具有挑战性的任务。现有的基于流和基于核的方法必须在噪声小且模糊度低的图像上进行帧插值。它们也无法有效处理EM图像上的大变形。
在本文中，我们提出了一种稀疏自注意力聚合网络，以根据生物组织的连续性合成像素。首先，我们开发了一种用于连续EM图像插值的注意力感知层，该层隐式采用全局感知变形。其次，我们提出了一种自适应风格平衡损失，考虑了连续EM图像的风格差异，如模糊和噪声。在注意力感知模块的引导下，自适应地合成从全局域聚合的每个像素，进一步提高了像素合成的性能。定量和定性实验表明，所提出的方法优于现有方法。
所提出的方法可被视为一种从全局域对每个像素与其他像素之间的关系进行建模的有效策略。这种方法提高了算法对噪声和大变形的鲁棒性，并且能够准确预测缺失区域的有效信息，这将极大地促进神经生物学研究的数据分析。
